cover
Contact Name
Ardi Susanto
Contact Email
ardisusanto@poltektegal.ac.id
Phone
-
Journal Mail Official
informatika.ejournal@poltektegal.ac.id
Editorial Address
Gedung B, Politeknik Harapan Bersama, Jl Mataram No 9 Pesurungan Lor Kota Tegal
Location
Kota tegal,
Jawa tengah
INDONESIA
Jurnal Informatika: Jurnal Pengembangan IT
ISSN : 24775126     EISSN : 25489356     DOI : https://doi.org/10.30591
Core Subject : Science,
The scope encompasses the Informatics Engineering, Computer Engineering and information Systems., but not limited to, the following scope: 1. Information Systems Information management e-Government E-business and e-Commerce Spatial Information Systems Geographical Information Systems IT Governance and Audits IT Service Management IT Project Management Information System Development Research Methods of Information Systems Software Quality Assurance 2. Computer Engineering Intelligent Systems Network Protocol and Management Robotic Computer Security Information Security and Privacy Information Forensics Network Security Protection Systems 3. Informatics Engineering Software Engineering Soft Computing Data Mining Information Retrieval Multimedia Technology Mobile Computing Artificial Intelligence Games Programming Computer Vision Image Processing, Embedded System Augmented/ Virtual Reality Image Processing Speech Recognition
Articles 487 Documents
Implementasi Content-Based Filtering Menggunakan TF-IDF dan Cosine Similarity untuk Rekomendasi Buku Akademik Mahasiswa Yunisa Salsabila Anggraeni; Septiana Dewi Saputri; Tania Azzahra; Aloysius Gonzaga Verrel; Vitri Tundjungsari
Jurnal Informatika: Jurnal Pengembangan IT Vol 11, No 2 (2026)
Publisher : Politeknik Harapan Bersama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30591/jpit.v11i2.10055

Abstract

The abundance of digital book collections in academic libraries creates information overload, making it difficult for students to find relevant references. This study aims to design and evaluate an academic book recommendation system based on Content-Based Filtering (CBF) using TF-IDF for text feature weighting and Cosine Similarity for measuring inter-content similarity. The dataset consists of 10 simulated academic book entries from Kaggle, covering title, author, category, and description attributes across Computers, Technology Engineering, and Mathematics domains. Methodological stages include text preprocessing, TF-IDF feature extraction, similarity matrix construction, and top-N recommendation selection. Evaluation was conducted through subjective satisfaction testing involving 10 student respondents and quantitative evaluation using Precision@K and Recall@K metrics. Satisfaction results showed recommendation relevance (87%), system speed (90%), ease of use (85%), and overall satisfaction (86%). Quantitative evaluation revealed limitations with Mean Precision@5 of 0.0921, Mean Recall@5 of 0.0772, Mean Precision@10 of 0.0815, and Mean Recall@10 of 0.1136, exhibiting a consistent precision-recall trade-off. The system is concluded to be functionally effective but semantically limited. Future development is recommended to integrate word embedding techniques such as Word2Vec or BERT alongside hybrid filtering to substantially improve system performance.
Sentiment Analysis of Shopee Application Reviews Using Multinomial Naïve Bayes and Bigram Feature Extraction Viktor Wahyu Nugroho; L.Budi Handoko
Jurnal Informatika: Jurnal Pengembangan IT Vol 11, No 2 (2026)
Publisher : Politeknik Harapan Bersama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30591/jpit.v11i2.10074

Abstract

The rapid growth of e-commerce in Indonesia has made user reviews a critical source of feedback, yet discrepancies between star ratings and actual sentiment often mislead businesses. This study employs the Multinomial Naïve Bayes algorithm to analyze sentiment in 25,000 Shopee application reviews collected via web scraping. The research utilizes TF-IDF for feature extraction and Bigram analysis to capture contextual meaning, addressing the challenge of imbalanced data (82% positive, 18% negative). The objective is to accurately classify user sentiment into positive and negative categories to provide actionable insights beyond numerical ratings. The model achieved a classification accuracy of 91.96%, with a high Recall of 77% for the minority negative class, ensuring effective identification of user complaints. Bigram analysis revealed that "delivery speed" is the primary driver for both satisfaction and dissatisfaction. The study confirms that Naïve Bayes is a robust and scalable solution for large-scale sentiment analysis in the Indonesian e-commerce context, offering a reliable tool for business intelligence. These findings emphasize the importance of text-based analysis over traditional rating systems, helping developers prioritize service enhancements.
Optimasi Model XGBoost Dengan Seleksi Fitur Mutual Information Dan Threshold Tuning Untuk Deteksi Intrusi Jaringan Vicola Nanda Pratama; Wildanil Ghozi
Jurnal Informatika: Jurnal Pengembangan IT Vol 11, No 2 (2026)
Publisher : Politeknik Harapan Bersama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30591/jpit.v11i2.10064

Abstract

Network Intrusion Detection Systems (NIDS) are essential for protecting networks from evolving cyber threats. Although Machine Learning can be relied upon for NIDS, challenges remain in achieving high accuracy while maintaining low false alarm rates. This research proposes an optimized NIDS framework using the Extreme Gradient Boosting (XGBoost) algorithm, which is enhanced through systematic feature selection and hyperparameter tuning. The methodology integrates a two-stage feature selection process that combines ExtraTreesClassifier for initial importance analysis and SelectKBest with mutual information for identifying the optimal feature subset. Hyperparameter optimization is performed using RandomizedSearchCV with 5-fold cross-validation, followed by threshold calibration to balance the False Positive Rate (FPR) and False Negative Rate (FNR). The model is trained and evaluated on the UNSW-NB15 dataset, which contains 257,673 network traffic records with binary classification (normal vs. attack). The results of the experiment show that the optimized XGBoost model achieved an accuracy of 95.4%, precision of 94.81%, recall of 95.29%, F1-score of 95.04%, and a significantly reduced FPR of 5.09%. The feature selection process identified 37 most informative features from the original 42 features, which contributed to improved model performance and efficiency. These findings indicate that an integrated approach of adaptive feature selection and systematic model optimization effectively improves intrusion detection performance, offering a robust and balanced solution for modern network security applications.
Pemanfaatan Metode Agile dalam Pengembangan Aplikasi CISEA pada PT. Bukit AsamTbk Risma Nur Aini; Allsela Meiriza; Dinna Yunika Hardiyanti; Khoirusy Syafaat
Jurnal Informatika: Jurnal Pengembangan IT Vol 11, No 1 (2026)
Publisher : Politeknik Harapan Bersama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30591/jpit.v11i1.10083

Abstract

Key Performance Indicator (KPI) management is a crucial aspect in measuring and evaluating organizational performance in a systematic and sustainable manner. However, KPI management processes that are still conducted manually may lead to several issues, such as verification delays, lack of data integration, and low accuracy in performance reporting. This study aims to develop an Electronic Balanced Scorecard (e-BSC) module within the CISEA application to support integrated and digital-based KPI management. The system development method employed in this study is Agile, which consists of planning, design, development, testing, documentation, and deployment stages. During the planning stage, system requirements were analyzed through observations and discussions with relevant stakeholders. The design stage utilized Unified Modeling Language (UML) to model the system, database structure, and user interface. System implementation was carried out using PHP as the programming language and MySQL as the database management system, with the user interface developed using HTML and CSS. System testing was conducted using the black box testing method to ensure that all system functions operated in accordance with user requirements. The results of this study indicate that the developed e-BSC module is capable of facilitating KPI input, verification, approval, and performance reporting processes in a more systematic, integrated and structured manner. Therefore, the system is expected to enhance the quality of organizational performance management and support accurate and timely managerial decision-making.
Klasifikasi Pemanfaatan Ekstrak Bunga Sepatu Menggunakan Naïve Bayes dan Word Cloud Nia Saurina; Khansa Tsabita Aqila; Alya Shafira Azizah; Udik Pudjianto
Jurnal Informatika: Jurnal Pengembangan IT Vol 11, No 2 (2026)
Publisher : Politeknik Harapan Bersama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30591/jpit.v11i2.10045

Abstract

 Hibiscus flower extract (Hibiscus rosa-sinensis L.) has been widely studied and utilized in various fields. Nevertheless, a structured depiction of its utilization patterns based on existing scientific literature remains unavailable. This study seeks to systematically map and examine the primary focus areas of hibiscus flower extract usage by employing Word Cloud visualization alongside Naïve Bayes classification techniques. The core dataset consisted of research abstracts retrieved from Google Scholar, PubMed, and ScienceDirect over the past ten years. Additionally, data from social media platforms (Twitter/TikTok) were gathered as a supplementary source to capture public perceptions. All collected texts underwent preprocessing steps including stopword removal and stemming prior to analysis. The resulting Word Cloud highlighted the most prominent terms: "hibiscus flower," "extract," "antimicrobial," "natural dye," "cosmetics," "antioxidant," "antibacterial," "skin care," and "medicinal plant"—findings that were further supported by high classification probabilities derived from the Naïve Bayes model. When evaluating three Naïve Bayes kernels in combination with Word Cloud visualization, the Multinomial Naïve Bayes  using a 90:10 training-to-testing data split achieved optimal performance, yielding an accuracy of 88.42%, precision of 87.91%, recall of 88.15%, and an F1-score of 88.03%. Moreover, the Word Cloud revealed that the "Health" category dominated academic discussions (42%), featuring keywords such as herbal, blood pressure, and antioxidant. This was followed by the "Research" category (35%) with terms like extract, test, and flavonoid, and the "Beauty" category (23%) focusing on skin, mask, and anti-aging—identifying a promising direction for future research.
Sistem Monitoring Keamanan Kamar Mandi Pintar Menggunakan ESP32 dan Sensor PIR Berbasis Internet of Things (IoT) Ansori Ansori; Nur Azizah; Firman Jaya
Jurnal Informatika: Jurnal Pengembangan IT Vol 11, No 2 (2026)
Publisher : Politeknik Harapan Bersama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30591/jpit.v11i2.10050

Abstract

This research addresses the problem of undetected falls and hazardous incidents in household bathrooms, especially for children and elderly users who are vulnerable to slipping on wet and narrow surfaces. The study aims to design and implement a smart bathroom security monitoring system using an ESP32 microcontroller, PIR sensor, magnetic sensor, load cell with HX711, and MPU6050 that is connected to the Internet of Things to provide real-time notifications to caregivers via mobile applications. The methodology follows a prototype-based IoT engineering approach, starting from literature review and requirement analysis, followed by hardware–software design, prototyping, iterative testing, and final evaluation in a simulated bathroom environment for various fall scenarios. Experimental data consist of PIR logs, weight changes, system response times, and environmental conditions, which are analyzed statistically to determine accuracy, reliability, and responsiveness of the system. The results show that the prototype is able to detect suspicious motion and fall patterns with good accuracy and trigger local alarms and Telegram notifications within approximately 2–3 seconds, while remaining operable in humid bathroom conditions. It can be concluded that the proposed system meets the research objectives as a low-cost, privacy-preserving bathroom safety solution for smart homes, with future work directed toward integrating machine learning-based fall detection and expanding communication options beyond WiFi to enhance robustness in diverse residential environments. 
Prioritas Risiko Keamanan Siber Berbasis Fuzzy Tsukamoto pada Assesmen Cybersecurity Zain Jamal Husain; Arry Maulana Syarif
Jurnal Informatika: Jurnal Pengembangan IT Vol 11, No 2 (2026)
Publisher : Politeknik Harapan Bersama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30591/jpit.v11i2.10363

Abstract

Increasing cyber threats require organizations to adopt measurable mechanisms for cybersecurity risk prioritization. The Cyber Security Maturity (CSM) framework issued by Badan Siber dan Sandi Negara is widely used to assess cybersecurity capability; however, its results remain descriptive and lack computational support for prioritization. This study proposes a cybersecurity risk prioritization model using Fuzzy Logic Tsukamoto, with maturity values from five CSM aspects as input variables. A total of 100 simulated datasets were generated using a rule-based scenario approach to represent diverse maturity conditions. Trapezoidal and triangular membership functions were applied, and the fuzzy rule base consisted of 15 rules based on the weakest-link principle. Results show that 88% of the data include at least one aspect in a transition zone and are consistently processed by the model. The output produces a distribution of 46% low, 44% medium, and 10% high risk within a 0–100 range, providing a structured, measurable, and reproducible prioritization approach.
Analisis Sentimen Komentar YouTube pada Channel Edukasi Otomotif menggunakan IndoBERT Farkhan Al Fanani Ruwanto Putra; L Budi Handoko
Jurnal Informatika: Jurnal Pengembangan IT Vol 11, No 2 (2026)
Publisher : Politeknik Harapan Bersama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30591/jpit.v11i2.10216

Abstract

The rapid growth of digital platforms like YouTube has generated massive volumes of unstructured user feedback, presenting significant challenges for manual analysis due to the prevalence of informal language and extreme class imbalances in sentiment distribution. This study addresses these issues by developing a robust sentiment classification system for Indonesian YouTube comments within the automotive education domain, leveraging the IndoBERT pre-trained transformer model to effectively handle linguistic variability and data disparity. The research methodology employs an IndoBERT-base model fine-tuned on a labeled dataset of 9,844 comments, integrating a comprehensive preprocessing pipeline for slang normalization and a Random Over Sampling (ROS) strategy to mitigate the bias toward majority classes. Experimental findings demonstrate that the proposed model achieves a commendable overall accuracy of 80.99%, with specific F1-scores of 0.84 for positive, 0.73 for neutral, and 0.72 for negative sentiments, significantly outperforming traditional baseline methods. Notably, the application of ROS successfully improved the recall rate for the minority negative class from 45% to an impressive 68%, ensuring better sensitivity to critical feedback. In conclusion, the integration of IndoBERT with targeted data optimization techniques offers a resilient solution for analyzing public opinion on social media, proving that transformer-based architectures can overcome the complexities of under-resourced languages and imbalanced data distributions to provide actionable insights for content creators.
Prediksi Kadar Alpha Pinene Minyak Terpentin Berdasarkan Komposisi Bahan Baku Menggunakan Regresi Linear Berganda Nisrina Nur Sa'idah
Jurnal Informatika: Jurnal Pengembangan IT Vol 11, No 1 (2026)
Publisher : Politeknik Harapan Bersama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30591/jpit.v11i1.9066

Abstract

Minyak terpentin merupakan produk hasil penyulingan getah pinus. Minyak ini memiliki nilai ekonomi yang tinggi, terutama karena kandungan alpha pinenenya yang menentukan kualitas produk minyak terpentin. Standar industri menetapkan kadar ideal alpha pinene adalah ≥ 80%. Namun, beberapa produksi minyak terpentin di Pabrik Gondorukem dan Terpentin (PGT) menghasilkan kadar di bawah standar, yang bisa mengurangi daya tarik pasar. Karena itu, penelitian ini berfokus pada pengembangan model prediksi kadar alpha pinene berdasarkan komposisi bahan baku getah pinus. Penelitian ini menggunakan metode regresi linear berganda dengan data sekunder dari Perum Perhutani, mencakup enam variabel input (Super Premium (SP), Premium (P), Mutu IA (IA), Mutu IB (IB), Mutu IIA (IIA), dan Mutu IIB (IIB)) dan satu variabel target (kadar alpha pinene). Tahapan penelitian meliputi pra-pemrosesan data, perancangan model (manual dan Python), perhitungan prediksi, dan evaluasi. Hasilnya, model menunjukkan tingkat kesalahan prediksi yang rendah: MAE 0,01312, MSE 0,00026, dan RMSE 0,01622. Namun, nilai R-squared hanya 0,20854, artinya model hanya menjelaskan sekitar 20,854% variabilitas data. Hal ini mengindikasikan bahwa terdapat faktor lain yang juga memengaruhi kadar alpha pinene, seperti kondisi hulu (genetik, lingkungan, penanganan) dan hilir (proses pengolahan). Oleh karena itu, eksplorasi dan pengembangan model lebih lanjut sangat diperlukan untuk akurasi yang lebih tinggi dan pemahaman yang lebih komprehensif.
Pemanfaatan Algoritma Eclat Dalam Penemuan Pola Transaksi Penjualan Produk Haircare Bangkit Ardi Nugroho; Sri Siswanti
Jurnal Informatika: Jurnal Pengembangan IT Vol 11, No 2 (2026)
Publisher : Politeknik Harapan Bersama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30591/jpit.v11i2.10148

Abstract

The professional haircare industry in Indonesia has experienced rapid growth, requiring companies to manage inventory more accurately and in a data-driven manner. Inefficient inventory management may lead to overstock or stockout conditions, resulting in operational inefficiencies and lost sales opportunities. This study aims to apply the Eclat algorithm to identify sales transaction patterns of professional haircare products at Inaura, to uncover significant product association patterns, and to formulate inventory management recommendations based on the analysis results. The research employs a quantitative data mining approach using market basket analysis. The dataset consists of sales transaction records of professional haircare products at  Inaura from January to December 2024. The Eclat algorithm is implemented with a minimum support threshold of 5% and a maximum itemset length of four items to generate frequent itemsets and meaningful association rules. The results indicate that the Eclat algorithm effectively and efficiently identifies sales transaction patterns that represent customer purchasing behavior. Products such as neutralizers, oxidising creams, and straightening systems exhibit the highest support values and form functional and complementary purchasing patterns. The extracted patterns can be utilized to support inventory planning, product prioritization, and data-driven bundling strategies. This study provides practical contributions to inventory optimization at Inaura and academic contributions by demonstrating the application of the Eclat algorithm in the underexplored domain of the professional haircare industry.